This study presents a novel approach for the diagnosis of luminal A breast cancer, a subtype characterized by positive hormone receptor expression and negative HER2 expression, using a 3D Convolutional Neural Network (CNN) based quantitative imaging biomarker (QIB) obtained from Magnetic Resonance Imaging (MRI). We employ a binary classification strategy to distinguish between luminal A and non-luminal A lesions by analyzing 3D volumetric MRI images. The proposed method allows the extraction and analysis of spatial information, which is essential for accurately diagnosing breast cancer, especially for the luminal A subtype, as it can present specific morphological characteristics. We aim to improve the diagnostic accuracy and efficacy of the ”luminal A” phenotype of breast cancer and contribute to developing personalized treatment plans for patients. The performance of the proposed method was evaluated using a public-domain breast cancer dataset (Duke-Breast-Cancer-MRI) and compared with traditional 2D CNNs approaches and other machine-learning techniques. In experimental settings, we achieved an AUC score of 0.9786 and an F1-score of 0.9502, representing a significant improvement level, regarding defined baseline approaches. Achieved results show the potential of this work to improve the diagnosis of breast cancer luminal A phenotype.