This paper presents a texture based approach for distinguishing mass from normal breast tissue in a mammogram. Identification of high probability area as mass is done on the basis of statistical features obtained from Gray-Level-Co-occurrence Matrix (GLCM) of mammogram image. The input mammogram is first pre-processed to remove the labeling artifacts and enhanced using adaptive histogram equalization. Unwanted details from the mammogram are excluded on the basis of block processing and histogram based features are extracted. Features based on GLCM are computed and analyzed to distinguish a suspicious mass from a non-mass region. Obtained results are promising in terms of correct classification. Contrast and energy measure from GLCM and mean, standard deviation and entropy helps to appropriately differentiate malign mass and normal tissue area.