Image mining is more than just an extension of data mining to image domain but an interdisciplinary endeavor. Very few people have systematically investigated this field. Clustering medical images for intelligent decision support is an important part in domain-specific application image mining because there are several technical aspects which make this problem challenging. In this paper, we firstly quantify the domain knowledge about brain image, and then incorporate this quantified measurement into the clustering algorithm. Our algorithm contains two parts: (1) clustering regions of interest (ROI) detected from brain image; (2) clustering images based on the similarity of ROI. We apply the method to cluster brain images and present results to demonstrate its usefulness and effectiveness.