Segmenting structures of interest represents one of the most important stages in the processes of interpreting, classifying and diagnosing analyses for Computer Aided-Diagnosis schemes. In this work, a method to segment microcalcification clusters in mammograms is proposed which is based on a differential filter, associated to the classic Sobel filter, in a pre-segmentation step (Step 1). This process will identify the significant pixels, which means that they will have the same value in both resultant images at each filtering processes. Also, two morphologic operations, a classic dilatation scheme and the proposed filter in multidirectional format are applied to obtain better border definitions and filled in regions of interest. In the next step (Step 2), an image map is obtained by translating a template in almost all possible image positions generating a vector of densities, formed by counting significant pixels. This discrete function makes it possible to find maximum points which will represent the possible microcalcification clusters. An algorithm to transform areas into single points is proposed to enable counting how many possible microcalcifications there are inside these regions. Tests with two databases composed of full mammograms and regions of interest with phantom images are presented with its respective performances.