Similar case retrieval apparatus, an image feature extracting unit for extracting a plurality of image feature quantity from the image to be interpreted as (150), the first of which is information indicating the existence range of values of each type of image feature amounts for the interpretation items Based on the interpretation knowledge, interpretation items matching degree calculating section for calculating the fitness of each interpretation items extracted plurality of image feature amount (160), the interpretation field candidate display unit for displaying the image interpretation field fit is large (170 ) and, interpretation item selecting section for selecting an interpretation items and (180), based on a predetermined second interpretation knowledge of association between the image feature amount and the image reading field, the extracted image feature per quantity in a plurality of image feature weight determining section that determines the weight of the larger value is strongly related to (190), which are extracted between the interpretation items selected as the image feature amount is included in the case data and a plurality of image feature amounts that are extracted from the medical image, by comparing by weighting the weight of the image feature quantity for each, is provided similar case retrieval unit for retrieving case data and (200).類似症例検索装置は、読影対象画像から複数の画像特徴量を抽出する画像特徴抽出部（１５０）と、各読影項目に対する画像特徴量の種類毎の値の存在範囲を示す情報である第一の読影知識に基づいて、抽出した複数の画像特徴量の各読影項目に対する適合度を算出する読影項目適合度算出部（１６０）と、適合度が大きい読影項目を表示する読影項目候補表示部（１７０）と、読影項目を選択させる読影項目選択部（１８０）と、各画像特徴量と各読影項目との間の関連性を予め定めた第二の読影知識に基づいて、抽出した画像特徴量ごとに、当該画像特徴量と選択された読影項目との間の関連性が高いほど大きな値の重みを決定する重み決定部（１９０）と、抽出された複数の画像特徴量と、症例データに含まれる医用画像から抽出される複数の画像特徴量とを、画像特徴量毎の重みで重み付けして比較することにより、症例データを検索する類似症例検索部（２００）とを備える。
