This article proposes a computer-aided diagnosis (CAD) system for the detection and identification of respiratory diseases, such as COVID-19, pneumonia, etc., in addition to differentiating a healthy case. Starting then, the proposal is comprised of the Discrete Wavelet Transform (DWT) with the Symlet10 function for the extraction of main features, together with the Limited Contrast Adaptive Histogram (CLAHE) method for contrast enhancement. For the classification of the cases, the Support Vector Machine (SVM) was used. The results showed considerable performance with the Medium Gaussian SVM model delivering 82.4% of correctly estimated values. Improve the capacity of detection and identification based on a supervised learning algorithm without the need to use high computational performance, considering that, in most of the health systems in Mexico, there is not the necessary hardware for the installation and operation of systems with high computational demand requirements.