Quantum computing techniques have shown promising results in tumor detection allowing these methods to combine the deep learning capabilities of convolutional neural networks with the processing power of quantum computer simulators, enabling efficient handling of large datasets and extraction of relevant tumor features. This paper focuses on hybrid quantum classifiers incorporating Convolutional neural networks (HQCNNs). Our study assesses the performance of an HQCNN architecture for brain tumor detection, exploring its performance with different qubit configurations. The model demonstrates remarkable potential, achieving a high classification accuracy of 95.5%, which highlights its promise as a valuable tool in medical diagnostics. A discussion of current limitations is arranged to use a physical Quantum Computer and detailed in the future research directions in quantum-based tumor detection.