A medical system comprises an image capture probe having a camera at its tip, a sensor system, and a processor. The processor is configured to receive an image from the camera when the image capture probe is located within an anatomic region of a patient anatomy; identify the tip's position based on information received from the sensor system; identify a tissue structure in the image; and define a subregion of a model of the anatomic region that corresponds to an area surrounding the tip. The processor is configured to compare the tissue structure to at least a portion of virtual tissue structures in the subregion to identify a best matched virtual tissue structure. The processor is configured to register the image to the model based on identification of the best matched virtual tissue structure to identify a virtual probe position for the tip with respect to the model.