Classification of breast tumors solely based on dynamic contrast enhanced magnetic resonance data is a challenge in clinical research. In this paper, we analyze how the most suspect region as group of similarly perfused and spatially connected voxels of a breast tumor contributes to distinguishing between benign and malignant tumors. We use three density-based clustering algorithms to partition a tumor in regions and depict the most suspect one, as delivered by the most stable clustering algorithm. We use the properties of this region for each tumor as input to a classifier. Our preliminary results show that the classifier separates between benign and malignant tumors, and returns predictive attributes that are intuitive to the expert.