Laser scanning is one of the most common techniques for the geometric documentation of historical buildings. The last decades, laser scanning has replaced or complemented traditional topographicmethods to a significant degree. The advantages of laser scanning that led to its high appreciation of the scientific community is that it is a fast method of geometric documentation that combines the accuracy of topographic and the wholeness of photogrammetric methods. The data that a laser scanner provides to the user is a large set of XYZ coordinates that is called point cloud. The point cloud needs to be processed so the information that it contains can be available and measurable. In this paper, the Principal Components Analysis (PCA) is being implemented to localize and extract pathology existed on planar walls of heritage buildings. PCA is a statistical procedure of identifying patterns in data. Also, it is being used to analyze data through dimensionality reduction and thus extracting information which is not immediately obvious. The building that was selected for the pathology localization is the GaziEvrenos Baths located at the city of Giannitsa in Greece.